The Three Gulfs Framework
October 8, 2025
Quick round of sharing:
Let’s take a moment to think
When working with AI, a recurring theme emerges:
Sound familiar? There’s a reason for this…
Three Gulfs Model - showing Developer, LLM Pipeline, and Data with the gulfs between them
This framework helps explain what you just experienced and guides our journey through this course
The challenge: Understanding your input data (scientific papers) and how your AI pipeline behaves on that data at scale.
What you just experienced:
Critical insight: We need systematic ways to understand our data and AI performance at scale
The challenge: The gap between what you want the AI to do and what you actually communicate in your prompts.
What you just experienced:
Key point: Seemingly clear instructions often contain hidden ambiguities
The challenge: Even with perfect prompts, AI may behave inconsistently across different inputs.
What you might experience next:
Important: Each application requires bridging the Three Gulfs anew - there are no universal solutions
Understanding the Three Gulfs helps us:
This week’s structure: We’ll address each gulf systematically through hands-on practice
Think about your hands-on session:
Most likely: You experienced all three! That’s completely normal.
Days 2-3: Addressing the Gulf of Specification - Systematic prompt engineering - Iterative refinement techniques
Day 3: Addressing the Gulf of Comprehension - Evaluation methodology - Understanding performance at scale
Days 4-5: Addressing the Gulf of Generalization - Real-world applications - Handling diverse paper types and use cases
Next: Collaborative discussion on expectations, concerns, and ethics (Session 1E)
Use of AI for Literature Review course, IAEA Laboratories, Seibersdorf, Austria, September 2025.